auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -56,9 +56,11 @@ more details, including on how to concatenate multi-part files.
|
|
| 56 |
| Link | Type | Size/GB | Notes |
|
| 57 |
|:-----|:-----|--------:|:------|
|
| 58 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled-i1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled.imatrix.gguf) | imatrix | 0.3 | imatrix file (for creating your own quants) |
|
|
|
|
| 59 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled-i1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled.i1-IQ1_M.gguf) | i1-IQ1_M | 8.3 | mostly desperate |
|
| 60 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled-i1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.6 | |
|
| 61 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled-i1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.6 | |
|
|
|
|
| 62 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled-i1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled.i1-IQ2_M.gguf) | i1-IQ2_M | 11.8 | |
|
| 63 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled-i1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled.i1-Q2_K_S.gguf) | i1-Q2_K_S | 12.3 | very low quality |
|
| 64 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled-i1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled.i1-Q2_K.gguf) | i1-Q2_K | 13.0 | IQ3_XXS probably better |
|
|
@@ -68,8 +70,11 @@ more details, including on how to concatenate multi-part files.
|
|
| 68 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled-i1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.9 | IQ3_S probably better |
|
| 69 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled-i1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled.i1-Q3_K_L.gguf) | i1-Q3_K_L | 18.2 | IQ3_M probably better |
|
| 70 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled-i1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled.i1-IQ4_XS.gguf) | i1-IQ4_XS | 18.8 | |
|
|
|
|
| 71 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled-i1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled.i1-Q4_K_S.gguf) | i1-Q4_K_S | 20.0 | optimal size/speed/quality |
|
| 72 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled-i1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled.i1-Q4_K_M.gguf) | i1-Q4_K_M | 21.3 | fast, recommended |
|
|
|
|
|
|
|
| 73 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled-i1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled.i1-Q6_K.gguf) | i1-Q6_K | 28.6 | practically like static Q6_K |
|
| 74 |
|
| 75 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
|
| 56 |
| Link | Type | Size/GB | Notes |
|
| 57 |
|:-----|:-----|--------:|:------|
|
| 58 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled-i1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled.imatrix.gguf) | imatrix | 0.3 | imatrix file (for creating your own quants) |
|
| 59 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled-i1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled.i1-IQ1_S.gguf) | i1-IQ1_S | 7.6 | for the desperate |
|
| 60 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled-i1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled.i1-IQ1_M.gguf) | i1-IQ1_M | 8.3 | mostly desperate |
|
| 61 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled-i1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.6 | |
|
| 62 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled-i1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.6 | |
|
| 63 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled-i1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled.i1-IQ2_S.gguf) | i1-IQ2_S | 10.8 | |
|
| 64 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled-i1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled.i1-IQ2_M.gguf) | i1-IQ2_M | 11.8 | |
|
| 65 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled-i1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled.i1-Q2_K_S.gguf) | i1-Q2_K_S | 12.3 | very low quality |
|
| 66 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled-i1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled.i1-Q2_K.gguf) | i1-Q2_K | 13.0 | IQ3_XXS probably better |
|
|
|
|
| 70 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled-i1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.9 | IQ3_S probably better |
|
| 71 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled-i1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled.i1-Q3_K_L.gguf) | i1-Q3_K_L | 18.2 | IQ3_M probably better |
|
| 72 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled-i1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled.i1-IQ4_XS.gguf) | i1-IQ4_XS | 18.8 | |
|
| 73 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled-i1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled.i1-Q4_0.gguf) | i1-Q4_0 | 19.9 | fast, low quality |
|
| 74 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled-i1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled.i1-Q4_K_S.gguf) | i1-Q4_K_S | 20.0 | optimal size/speed/quality |
|
| 75 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled-i1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled.i1-Q4_K_M.gguf) | i1-Q4_K_M | 21.3 | fast, recommended |
|
| 76 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled-i1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled.i1-Q5_K_S.gguf) | i1-Q5_K_S | 24.1 | |
|
| 77 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled-i1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled.i1-Q5_K_M.gguf) | i1-Q5_K_M | 24.8 | |
|
| 78 |
| [GGUF](https://huggingface.co/mradermacher/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled-i1-GGUF/resolve/main/Qwen3.5-35B-A3B-heretic-v2-Opus-4.6-Distilled.i1-Q6_K.gguf) | i1-Q6_K | 28.6 | practically like static Q6_K |
|
| 79 |
|
| 80 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|